Water Quality Index Calculation of River Ganga using Decision Tree Algorithm

International Research Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

e ISSN: 2395 0056

p ISSN: 2395 0072

Water Quality Index Calculation of River Ganga using Decision Tree Algorithm

Shyam Dwivedi6

1,2,3,4,5Student of B. Tech Final year, Department of Computer Science and Engineering, Rameshwaram Institute of Technology & Management, Affiliated to AKTU, Lucknow, U.P ,India

6Assistant Professor & Head of Department, Department of Computer Science and Engineering, Rameshwaram Institute of Technology & Management, Affiliated to AKTU, Lucknow, U.P, India

***

Abstract - The Ganga is not only a pious river, but also a way of life for many citizens of India .It has cultural, spiritual as well as scientific importance. Our project research is based entirely on Machine Learning Application . Rapid urban sprawl, industrial development and high demand for water have caused major problems with water quality degradation and deterioration . Therefore, the aim of our project is to analyze the water quality of the Ganga River for three different seasons basically Summer, Monsoon and Winter to assess whether Ganga river water is potable or not. Rivers are under heavy degradation due to human activities such as dumping of waste, industrial activities, mining in the river, the water level of the river has dropped dramatically which has affected marine life and human health. The method we use in our research is to design a machine learning model based on ML algorithm which will calculate WQI and provide measurement of river water quality that will be used to determine whether the water is drinkable or not. It will be a python based WQI calculator.

Key Words: Machine Learning, Decision Tree, WQI

1. INTRODUCTION

GangaRiverisconsideredasthemostprominentriverofIndia.UsinglatesttechnologieslikeMachineLearningandPython FrameworkFlask,wearegoingtocreateamachinelearningmodelwhichwillpredictthequalityoftheGangariverwater wherethemeasuringparametersdatasetiscollectedfromthewebsiteofUCIRepository.Basedonthiscollecteddatafrom different citieswhereGanga riverbedishuge, the model will betrainedandthe prediction algorithm which will bemost accurateandprecisewillbeused.

1.1 Machine Learning (ML) isthestudyofcomputersciencewherealgorithms canbeusedtomakedecisionsonitsown anddecisionscanbeimprovedthroughlearningandpastexperiences.Itisoneofthesubsetsofartificialintelligence.Machine learningalgorithmsbuildmodelsbasedontrainingdatasetsorsampledatatomakepredictionsordecisionswithoutbeing explicitlyprogrammed.Nowadays,MachineLearningcanbeseenineveryfieldsuchasthehealthsector,financesector, Aeronauticalsector,Agriculture,emailfiltering,voicerecognition,speechrecognition,andcomputervision,etcanditisquite noteasytodeveloptraditionalalgorithmstoperformthetaskswhichML modelscaneasilydo. Machinelearningusesdata andlearnsfromthatdataforbetterfuturepredictions.Machinelearningmodelscanbeimprovisedmorebyeffectivehandling oftrainingdatasetsothatnooverfittingandunderfittingcomesintopicture.

Thethreemaintypesofmachinelearningtasks:supervisedlearning,unsupervisedlearning,andreinforcementlearning.

International Research Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

e ISSN: 2395 0056

p ISSN: 2395 0072

1.1.1 Supervised Learning,asetofexamples(i.e.thetrainingset)issubmittedtothesystemasinputduringthetraining phase.Eachinputislabeledwiththedesiredoutputvalue,sothesystemknowswhattheoutputwilllooklikewhentheinput comesin.Forexample,considersomeexperimentalobservationsthatcanbegroupedintoNdifferentcategories.Sowehavea trainingset(apairofsequences){(x1,y1),(x2,y2)…..(xn,yn)},wherexiistheinputandyiistheclassofthecorresponding output.Trainingisperformedbyminimizingaspecificcostfunctionrepresentingthebindingsfromtheinputxiandthedesired outputyi.

1.1.2 Unsupervised Learning providestrainingexamplesthatarenotlabeledwiththeclasstowhichtheybelong.Therefore, the system develops and organizes data, looking for common characteristics among them and making changes based on internalknowledge.

1.1.3 Reinforcement Learning is a machine learning training method based on rewarding desirable behaviors and or punishing unwanted behaviors. In general, reinforcement learning agents can recognize, interpret, take action, and learn throughtrialanderrorintheirenvironment.

1.2 Machine Learning Algorithm (Decision Tree )

DecisionTreeisanon parametricsupervisedlearningmachinelearningalgorithmusedforclassificationandregression.Itisa treestructuredclassifierwhereinternalnodesrepresentthefeaturesofthedataset,branchesrepresentthedecisionruleand leafnodesrepresenttheoutcomeanddonotcontainfurtherbranches.Theobjectiveistocreateamodelthatpredictsthevalue ofatargetvariablebylearningatrainingdatasetofdecisionrulestakenfromthedatafeatures.DecisionTreeClassifierisa classificationalgorithmcapableofperformingmultipleclassclassificationonadataset.Aswithotherclassifiers,DecisionTree Classifiertakesasinputtwoarrays:anarrayX,sparseordense,ofsizensamples,n featuresholdingthetrainingsamples,and anarrayYofintegervalues,sizen samples,holdingtheclasslabelsforthetrainingsamples.

Adecisiontreeisaoneofthetypesofsupervisedmachinelearningalgorithmswhereboth inputandoutputdataare labeled. ItcanbeusedforbothCategoricalandContinuousOutput.Thedatasetiscontinuously dividedintosubtreesbasedonsome parameter and calculationmeasure until the final output is achieved. A Decision Tree can be explained by two entities, decisionnodesandleafnodes.Leafnodes aredecisionsorendresultswhere furtherdivisionofnodeswillnotbepossible .Decisionnodesarethenodeswheredataissplitandfurthersub treesaregenerated.

DecisionTree MainComponents:

 RootNode:Thenodefromwherethedecisiontreestarts.Itrepresentstheentiredatasetwhichfurthergetsdivided intotwoormoresets.

 LeafNode:Theleafnodesarethefinaloutputsandtreecannotbesegregatedfurthermoreaftergettingtheleafnode asitisthefinaloutput.

 Pruning:Theprocessofremovingunwantedbranchesfromthetreetoreducecomplexityandambiguity.

 ChildNode:Thesegregatednodesarechildnodes.

International Research Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

1.2.1 Algorithm for Decision Tree

Step 1 :Beginthetreewiththerootnodewhichcontainsthecompletedataset.

Step 2: ThebestattributeinthedatasetusingAttributeSelectionMeasureisselected.

Step 3:Dividethedatasetintosubsetsthatcontainallpossiblevaluestoachievethebestattribute.

Step 4 :Thedecision tree nodewhichcontainsthebestattributeisgenerated.

e ISSN: 2395 0056

p ISSN: 2395 0072

Step 5 :Recursivelynewdecisiontreesarecreatedusingthesubsetsofthedatasetcreatedinstep3.Thisprocessiscontinued untilthefinalstageisreachedcalledleafnodewhenfurthersegregationwillnotbepossible.

Therearetwotypesofdecisiontrees:

Classification trees : Thedecisionvariableis0or1typeor Yes/NocalledasCategoricalValue. Regression trees : ThedecisionortheoutcomevariableisContinuousinnature,forexample,a numberlike187.

Therearemanyalgorithmsbywhich DecisionTreescanbeconstructed,butoneofthebest iscalledtheID3Algorithm.ID3 StandsforIterativeDichotomiser

1.2.2 Entropy: Entropy,alsoknownas ShannonEntropyisdenotedbyH(S)forafinitesetS,whichisthemeasureofthe amountofuncertaintyorrandomnessinthedata.IntheMachineLearningparadigm,entropymeasuresunpredictabilityand impurity,it isrelatedtorandomnessintheinformationbeingprocessedinthemachinelearningproject.

Entropy(S)= (P(y) P(y) P(n) P(n))

1.2.3 Information gain: InformationgainisalsocalledtheKullback Leiblerdivergence,denotedIG(S,A)forasetS,whichis theeffectiveentropychangeafterselectingacertainattributeA.Itmeasurestherelativeentropychangewithrespectto independentvariables.

InformationGain=Entropy(S) {(weightedaverage)*Entropy(Eachfeature)}

Alternatively, whereIG(S,A) istheInformationgainbyimplementing featureA,H(S)isthe Entropyofthe entire dataset, istheEntropyafterapplyingthefeatureAand P(x)istheprobabilityofeventx.

1.3. Iterative Dichotomiser ID3 Algorithm isa classificationalgorithmthatfollowsthegreedyapproachofdecision treesbyselectingtheoptimalattributesthatproducethemaximuminformationgain(IG)orminimumentropy(H).

I(p,n) =entropyofadataset

. =weightedsummationofthelogsoftheprobabilitiesoftheeachpossibleoutcome = [(p/(p+n)) (p/(p+n))+(n/(p+n)) (n/(p+n))]

ID3 procedure :

 Calculatetheentropyofthedataset.

 Foreachattribute/feature.

 Calculateentropyforallitscategoricalvalues.

Factor value: 7.529

International Research Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

 Calculateinformationgainofthefeature/attribute.

 Findthefeaturewithmaximuminformationgain.

 Choosethefeaturewithmaximuminformationgainastherootnodeforthetree.

 Repeattheabovestepsuntil thedesiredtreeisobtained.

2. PROJECT OBJECTIVES

e ISSN: 2395 0056

p ISSN: 2395 0072

The objectiveofthe machinelearningprojectis tocreateaWaterQualityIndex(WQI)CalculatorusingpythonandFlask whichwillanalyzethequalityof Gangariverwateranddecidewhetherthewaterissafefordrinkingbyscalingthewaterin thescoreof(0 100)

3. IMPLEMENTATION & METHODOLOGY

3.1 Study Area: ThepresentstudywasperformedtostudythesurfacewaterqualityintheriverbedmovingareaofGanga Riveratdistrictnamely;Varanasi,Kolkata,Jahangirpur,andTribeni.

3.2 Sampling Procedure and Methods of Analysis: ThephysicochemicalparametersusedinthisstudyarepH, Temperature,TotalDissolvedSolid,BiologicalOxygenDemand(BOD),DissolvedOxygen,Turbidity,Nitrate,Phosphateand FecalColiform.WehavecombineddatasetofourstudysitesinthreedifferentseasonsnamelySummer,MonsoonandWinter foreachofthedistricts.Wehavetrainedthecombineddata setonthebasisofmachinelearningalgorithmsandusedWater QualityIndexCalculationforQualitycheckingofwaterfordifferentcitiesindifferentseasonsandtocheckwaterisdrinkable ornot.Theparameterswhicharefinalizedafterpre processingofthedatasetaresomehowinterdependentoneachother.The modelwillbetrainedonthebasisoftheseninephysicochemicalparameterswhichwillbefurtherusedforcalculationofWater QualityIndexand decidingwaterisdrinkableornot.

FlowofModelCreation

1:TabledepictingmeanvaluesofparametersinStudySite

Impact Factor value: 7.529 | ISO 9001:2008

International

Volume: 09

Technology (IRJET)

e ISSN: 2395 0056

p ISSN: 2395 0072

3.3 Graphical Representation of Water Quality Index Calculating Parameters

These

different

3.3.1 pH: pHisascalingmethodology whichisusedtodeterminetheacidityorbasicityofanaqueoussolution.LowpHvalues denotes acidic character, while higher values denotes basic character of the solution. The pH scale is (0 14),where (0 7) denotesacidiccharacterand(7 14)denotesbasiccharacterofthesolution.ThebasicpHrangeforsurfacewateris:(6.5 8.5) .pHisthecrucialparameterassociatedwiththeothercalculatingparametersforWQIcalculation.AspHcanbeeasily affected byotherchemicalsinwater,pHisnecessarytobeaccurateforbestresultsofthemodel.pHiscalculatedinlogarithmicunitsof base10whichmeanseachnumberrepresentsa10 foldchangeinacidityorbasicitydependingonthepHvalue.

(pH=− (H+).

3.3.2 Temperature : Thesurfacewatertemperatureisusuallybetween(0 30)degreesCelsius.Thetemperatureisthewater parameterwhichrefersto howcoldorwarmthewateris.Inmonitoringwaterqualityandinfieldofscience,temperatureis basicallymeasuredindegreesCelsius.Watertemperatureaffectsalmosteveryotherwaterqualityparameter.Temperature affectsotherwaterqualityparameterstoagreatextent,alsocanchangethephysicalandchemicalpropertiesofwatertoo. Thevariedseasonaltemperaturefluctuationsmaybeduetochangesinairtemperature,solarangle,weatherevents,global warmingandtheamountofmaterialassociatedwiththestreamandwaterfeatures.

International Research Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

e ISSN: 2395 0056

p ISSN: 2395 0072

3.3.3 Total Dissolved Solid : TDSisameasureofthedissolvedsolventsfoundinanaqueoussolution.Infact,thisisanything thatcontaminatesthepurityofwater.Someofthesesolventscancausealargenumberofhealthproblems.TDSisanindicator ofwaterquality.HavingahighTDSdoesnotalwaysmeanthatwaterisdangerous.Forexample,somemineralwaterhasvery highlevelsofsolidsinsideandthisdoesnotseemtobedangerous,butthatisbecauserealsolidmaterialsare.Thisisusually Ca,Mgorothersubstancesthatmaynotbeharmfultothebody

300mg/L:Excellent (300−600)mg/L:Good (600−900)mg/L:Fair (900−1200)mg/L:Poor

Above1200mg/L:Unacceptable

3.3.4 Biological Oxygen Demand : BODisanotherprominentwaterqualitycalculationterm.AwatersupplywithaBODlevel of3 5ppmcanbeconsideredas moderate,withaBODlevelof6 9ppmwaterisconsideredcontaminatedbecausethereis usuallyanorganismpresentandgermsdecomposethewaste.WhenBODlevelsare100ppmormore,thewatersupplyis consideredtobehighlycontaminatedbyorganicwaste.Theneedforbiochemicaloxygenortheamountofoxygenneededto decomposeorganicmatterperone literofpollutedwater.Themorepollutedthewater,themoreBODwillbebecausemostof itwillbeorganicmatterand,asaresult,moreoxygenwillneedtodecompose.Itisthereforeareliablegaugeforthepollution oflargeamountsofwater.Oneofthemainreasonsfortreatingcontaminatedwaterbeforeitisdischargedfromawatersource istoloweritsBOD thatis,reduceitsoxygendemandandthusreduceitsneedforthewaterfromwhichitisreleased.

3.3.5 Dissolved Oxygen: Meltedoxygen(DO)isameasureofhowmuchoxygenisdissolvedinwater theamountofoxygen foundinaquaticorganisms.Theamountofoxygendissolvedinastreamorpondcantellusalotaboutwaterquality.Melted oxygensaturationisreportedinunitsofmg/l(mg/lisalsocalledinfractionspermillion(ppm)becauseitis1000gramsof purewater,andamilligramisafractionofamillionofthat).Percentagefilledspaceisreportedbypercentageunits.The oxygendissolvesinthewateruntilitisfull,thenormalamountofheatgiven.Percentagegaintellsuswhichpartofthecatch capacityisactuallytaken.ThehighlevelofDOinapublicwatersupplyisgoodbecauseitmakesdrinkingwatertastebetter. However,highlevelsofDOacceleratecorrosioninwaterpipes.

3.3.6 Phosphate: Phosphatesarethechemicalswhichcontaintheelementphosphorus,andtheyaffectthequalityofwaterby causing algaegrowthinahugeamount.Phosphorusnaturallyoccursinrocksandotherminerals.Duringthenaturalclimate process,rocksslowlyreleasephosphorusasphosphateionsdissolveinwaterandmineralizedphosphatecompoundsbreak down,Phosphates

PO4 3 are formed from this component. Phosphates basically exist in three forms: orthophosphate, metaphosphate (or polyphosphate)andorganicallyboundphosphate;eachcompoundcontainsphosphorusinadifferentchemicalsystem.These typesofphosphateoccurinfossilsoflivinganddecayingplants,suchasfreeorslightlyion bindingionsinaqueoussystems, chemicallysynthesizedinstructuresandsoils,orasmineralizedcompoundsinsoils,rocksandobjects.

3.3.7 Nitrate: Nitratecanalsocauseadversehealthaffectswhenpresentinhighquantity.TheEPAhasestablishedanofficial drinkingwaterstandardof10milligramsofnitrateperliterofwater(10mg/L).Thequestionariseshow doesnitrateaffect aquaticlife?Nitrateshavethesameeffectonaquaticplantgrowthasthephosphatesaswellasthesameadverseeffecton waterquality.Plantsandalgaegrowfastwhichprovidesfodderforfishwhichcouldleadtoanincreaseinthenumberoffish. Thedemeritofitisthat theoxygenlevelsinthewaterwilldropandthefisheswilldie.

Becausenitratecanbeshort livedinamodifiedformofnitrites,andbecausenitritescancauseseriousillnessinbothwildlife andhumans,theacceptablenitratelevelsindrinkingwaterhavebeendetermined as10mg/l.Pollutedwaterusuallycontains nitratelessthan1.0mg/l.

3.3.8 Turbidity : Turbititymeasurestherelativeclarityofthewater.Itisdefinedasthenumberofsuspendedparticlesin water.Debrisinthewateriscausedbyorganicmattersuchasclay,mud,dustandorganicmatteraswellasplanktonandother microorganismsthatinterferewiththepassageoflightcoming intothewater.Turbiditycanbereferredtoastotalsuspended solids(TSS)anditalsoinvolvesplanktonandotherorganisms.Naturalwatervariationstendtoriseduringheavyflowdueto increased ground runoff, river flow, and erosion. High turbidity can disturb the cleanliness and give an environment for bacterialgrowthaswellascanincreasethepresenceofmicrobesinwater.

© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page3916

International Research Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

e ISSN: 2395 0056

p ISSN: 2395 0072

3.3.9 Fecal Coliform :Theexistenceoffecalcoliformbacteriainfluvialareasdesignatethatwaterisinfectedwithhumanor animalfeces.Wheneverthishappens,thesourcewaterislikelytobeinfectedwithgermsorpathogens thatmaybepresentin thesoil.

3.4 Water Quality Index AWaterQualityIndex(WQI)isamethodologywherewaterqualityiscalculatedandanalyzed. JustlikeAirQualityIndexandUVIndex,itcalculatesindexlyinginparticularrangeand describeswhetherthequalityof water issafefordrinkingornotandultimatelyfinalizestheresultbyscalingthewaterindifferentscores.

The water quality indicator is a 100-point scale that summarizes the results from a total of nine different scales when

completed.Fieldvalues canbeconvertedtoindexvalues;respondents wereaskedaseriesofquestionstoincludeawater qualitylevelgraph(0to100)correspondingtofieldvalues suchaspH(2 12).Thecurvesarethenweighedandaredesignedto calculatetheoptimumresult.Thecalculatorcompletesindividualandgroupvalues andallowstherespondents togenerate customreportsofthewater.WQIcalculatorwilleventuallycreatescalingoftheriverwatertested

Inthisstudy,thecalculationof9analyzedphysicochemicalparametersi.e..PH,Temperature,SolidSolidCore,SolubleOxygen, Nitrate,Phosphate,BiologicalOxygenDemand,TurbidityandFecalColiformwereselectedtoassessthequalityoftheGanga Riverinthreedifferentperiods(Summer,Monsoon,Winter)onselectedsites.

© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page3917

International Research Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

e ISSN: 2395 0056

p ISSN: 2395 0072

TheQ valueforeachtestshouldbemultipliedbytheratingscaleshownontheWorksheetforeachtest,andthe answer shouldberecordedinthe“Total”column.Themeasurementfactorindicatestheimportanceofeachtestforoverallwater quality.Forexample,theweightingfactoroffecalcoliformis0.16,soitisconsideredmoreimportantinassessingtotalwater qualitythannitrate,withameasuringfactorofonly0.10.Finally,addthenumbersshownintheContentcolumntodetermine thetotalWaterQualityIndex(WQI)ofthetestedwatersource.CompareyourIndexresultwiththeratioshowninTableIto measurethewaterlevelofthetestedwatersupply

Thealgorithmusedinthisstudyis"DecisionTreeClassifier"sothewaterqualityaftercalculating9parametersis determined bycategoriesandeventuallyclassifiedintovariedclassesonqualityscaling.TheWaterQualityIndexCalculatorusesascaling from0to100tomeasurewaterquality,where100isthehighestscore.

4. RESULTS

Informationaboutriverwaterqualityisimportantfortheconservationandsurvivalofmarineanimals.People,somehow,rely onriverstomeettheirdailyneedsandhumaninterventioninriversmakeswaterlevelsworse.Tomaintainthisperspective, thecurrentstudywasdesignedtoassessthesurfacewaterleveloftheGangaRiverusingMLApplicationstoIoT.Inthepresent study,ninephysicochemicalparameterswereanalyzed.Thealgorithmusedinthisstudyis"DecisionTreeSeparator''sowater qualityaftercalculating9parametersisdeterminedinstages.TheWaterQualityIndexCalculator usesascaling from0to100 tomeasurewaterquality,where100isthehighestscore.OncealltheWQIpointsareknown,theycanbecollectivelyusedto determinehowhealthythewaterisonaparticularday.

WQI Scale : CATEGORY QUALITY

−100 :ExcellentWaterQuality

−90 :GoodWaterQuality

−70 :MediumoraveragewaterQuality

−50 :FairWaterQuality

−25 :PoorWaterQuality

International

Journal of Engineering and Technology (IRJET)

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net

4.1 Accuracy Score

e ISSN: 2395 0056

p ISSN: 2395 0072

Accuracyisametricfortheevaluationofclassificationmodels.Itisthefractionofpredictionsourmodelcalculatedright.

Accuracy = Number of Accurate Predictions / Total Total Predictions

Forbinarycalculations,accuracycanalsobecalculatedaccordingtothepositivesandnegativesasshownbelow:

Accuracy = (TP + TN) / (TP + TN + FP + FN)

whereTP=TruePositive,TN=TrueNegative,FP=FalsePositive,andFN=FalseNegative

5. CONCLUSION

ThepresentstudyinvestigatesthequalityofthesurfacewateroftheGangaRiverintheactiverivermineareaof Varanasi, Kolkata,Jahangirpur,andTribeni.ThestudyconcludedonthebasisoftheMLAlgorithmaccuracypointsindicatingthequality of water that was slightly polluted during heavy rainfall. at all sample sites. During the summer, WQI scores indicate an acceptablelevelofwaterqualityandduringthewinter,itreflectstheexcellentwaterqualityoftheGangaRiver.Thewater leveloftheGangaRiverisrecordedandpollutedduringstormsduetohighrunofffromtherivercomparedtosummerand winterseasons.Duringthe WQI qualityinspection,atleasta goodcondition wasrecordedduringheavyrains. Thestudy revealedthattheWQIoftheGangaRiverwasnotfoundtobesuitablefordrinkingpurposesduringtherainyseason,itmaybe suitableforirrigationpurposes.Theoutcomeofthiscurrentstudyrequirescarefulmonitoringoftheecologicalfeaturesofthe aquaticenvironmentespeciallyintheactiveGangariversduetothepotentialnaturalhazard.

5.1 Know Your Water Quality WehavemadeawebsitenamedKNOWYOURWATERQUALITYwhichwillpredictthequality statusofwater,allwehavetodoistofeedthedetailsof9parametersrequiredforWQIcalculation.

LINK:https://gangawaterproject.herokuapp.com/

International Research Journal of Engineering and Technology (IRJET)

e ISSN: 2395 0056

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p ISSN: 2395 0072

6 . FUTURE SCOPE

 AccuracyScorecanbefurtherimprovedandmoreparameterscanbeincludedintheWQICalculationforthebetter results.



Astudyanda websitecanbemadeformanyriversofIndiatogether.

 ThefuturescopeofthisstudyisthatitcanbefurtherdeployedonDjangoratherthanFlaskatthistimesothatUser Experience can be more interactive and an app can also be made for the same so that one can use it on their respectivesmartphones.

 As AQI is a prominent term due to high pollution in metropolitan cities ,Similarly WQI should also be in more considerationfortheriverinesystems.

REFERENCES

[1] A.K.Bisht,R.Singh,R.BhutianiandA. Bhatt,“ArtificialNeuralNetworkBasedWaterQualityForecastingModelforGanga River,”InternationalJournalofEngineeringandAdvancedTechnology(IJEAT)ISSN:2249 8958(Online),Volume 8Issue 6,August2019,pp2778 2785

[2] Y.SoniandV.Sejwa,“AnEstimatingModelforWaterqualityofriverGangausingArtificialNeuralNetwork,”International JournalofInnovativeTechnologyandExploringEngineering(IJITEE)ISSN:2278 3075,Volume 8Issue 9,July2019,pp 1448 1453

[3] A.K.Bisht,R.Singh,R.Bhutiani,A. BhattandK.Kumar,WaterqualitymodelingoftheRiverGangausingartificialneural networkswithreferencetothevarioustrainingfunctions,”EnvironmentConservationJournal18(1&2)41 48,April2017, pp 41 48.

[4] A.K.Haritash,S.GaurandS.Garg,”AssessmentofwaterqualityandsuitabilityofRiverGangainRishikesh,India,”Appl WaterSci(2016)6:383 392DOI10.1007/s13201 014 0235 1,pp382 392

[5] S.VijayandDr.K.Kamaraj,“GroundWaterQualityPredictionusingMachineLearningAlgorithmsinR”,IJRAR International JournalofResearchandAnalyticalReviews,eISSN2348 1269,VOLUME6IISSUE1IJAN. MARCH2019,pp743

BIOGRAPHIES IITBHUandiscurrentlyworkingonPythonandMachineLearning.

Kaushiki Agrahari : He is a student of B.Tech Final Year.Department of Computer Science Engineering ,RameshwaramInstituteofTechnologyandManagement.ShehascompletedaninternshiponMachineLearningfrom

AnkurKashyap:HeisastudentofB.TechFinalYear.DepartmentofComputerScienceEngineering,Rameshwaram InstituteofTechnologyandManagementandcurrentlyworkingonPythonandMachineLearningprojects.

Sakshi :She is a student of B.Tech Final Year,Department of Computer Science and Engineering ,Rameshwaram InstituteofTechnologyandManagement andcurrentlyworkingonPythonandMachineLearning.

value: 7.529

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 09 Issue: 04 | Apr 2022 www.irjet.net p-ISSN: 2395-0072

ShashankKumar: HeisastudentofB.TechFinalYear.DepartmentofComputerScienceEngineering ,Rameshwaram Institute of Technology and Management and currently working on Python and Machine Learningprojects.

ShivanshSharma:HeisastudentofB.TechFinalYear.DepartmentofComputerScienceEngineering , RameshwaramInstituteofTechnologyandManagementandcurrentlyworkingonPythonandMachine Learningprojects.

ShyamDwivedi HeiscurrentlyworkingasanAssistantProfessorandHeadofDepartmentinRameshwaram InstituteofTechnology&Management,Lucknow,India.HeisM.Tech 2012BITMesra,Ranchi,hehasateaching experienceof10yearsand1 yearinTCSIndustrialexperience.